Spatio-temporal Modeling and Analysis of Fmri Data Using Narx Neural Network

This paper presents spatio-temporal modeling and analysis methods to fMRI data. Based on the nonlinear autoregressive with exogenous inputs (NARX) model realized by the Bayesian radial basis function (RBF) neural networks, two methods (NARX-1 and NARX-2) are proposed to capture the unknown complex dynamics of the brain activities. Simulation results on both synthetic and real fMRI data clearly show that the proposed schemes outperform the conventional t-test method in detecting the activated regions of the brain.

[1]  Sadasivan Puthusserypady,et al.  Neural Networks for fMRI Spatio-temporal Analysis , 2004, ICONIP.

[2]  J. Duyn,et al.  Investigation of Low Frequency Drift in fMRI Signal , 1999, NeuroImage.

[3]  P. Bandettini,et al.  Spatial Heterogeneity of the Nonlinear Dynamics in the FMRI BOLD Response , 2001, NeuroImage.

[4]  Karl J. Friston,et al.  Analysis of fMRI Time-Series Revisited , 1995, NeuroImage.

[5]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[6]  Karl J. Friston,et al.  A unified statistical approach for determining significant signals in images of cerebral activation , 1996, Human brain mapping.

[7]  R. Buxton,et al.  Dynamics of blood flow and oxygenation changes during brain activation: The balloon model , 1998, Magnetic resonance in medicine.

[8]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[9]  J C Gore,et al.  An roc approach for evaluating functional brain mr imaging and postprocessing protocols , 1995, Magnetic resonance in medicine.

[10]  Stephen M. Smith,et al.  Functional MRI : an introduction to methods , 2002 .

[11]  R. Turner,et al.  Event-Related fMRI: Characterizing Differential Responses , 1998, NeuroImage.

[12]  R. Weisskoff,et al.  Effect of temporal autocorrelation due to physiological noise and stimulus paradigm on voxel‐level false‐positive rates in fMRI , 1998, Human brain mapping.

[13]  Angela R. Laird,et al.  Investigating the nonlinearity of fMRI activation data , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.

[14]  Karl J. Friston,et al.  Analysis of fMRI Time-Series Revisited—Again , 1995, NeuroImage.

[15]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[16]  Paul M. Matthews,et al.  Functional magnetic resonance imaging: An introduction to methods , 2001 .

[17]  E. Bullmore,et al.  Identifying Rate-Limiting Nodes in Large-Scale Cortical Networks for Visuospatial Processing: An Illustration using fMRI , 2001, Journal of Cognitive Neuroscience.

[18]  Georg Dorffner,et al.  Neural Networks for Time Series Processing , 1996 .